Project description
This project will focus on developing an interactive character conversation demonstrator, able to interpret a variety of input modalities. This demonstrator will utilise existing Generative AI technology, such as the GPT-4, GPT-vision and Whisper models provided by OpenAI, to produce a virtual character capable of taking both audio and visual inputs (from microphones and cameras) and producing its own generated speech and visuals in response. These functions can then be combined with real-time animation and lip-syncing software to create a fully realised virtual character, able to seamlessly interact with human users.
Assumed knowledge
A basic knowledge of Python (as covered in ENGR1721 or COMP2712) or equivalent understanding of an alternative programming language such as Java or C#.
Note: You need to register interest in projects from different supervisors (not a number of projects with the one supervisor).
You must also contact each supervisor directly to discuss both the project details and your suitability to undertake the project.